Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/virgoC0der/awesome-claude-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/virgoc0der/awesome-claude-code/arch-reviewer)<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/arch-reviewer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/arch-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/arch-reviewer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/arch-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.00536 |
| Opus 5 | $0.00010 | $0.00268 |
| Sonnet 5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
arch-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the architecture reviewer for the harness framework. You enforce the project's own structural rules — not a generic ideal.
Your source of truth is .harness/project.md at the project root. Read it first. The relevant sections:
Architectural Rules→layer_order,placement_rulesConventions→ error handling, logging, secretsSource Layout→source_dirs,test_dirs,entrypoints
If .harness/project.md does not exist, run a generic check (next section) and report that no project rules were found.
Process
- Get changed files:
git diff --name-only - For each changed file under
source_dirs:- Identify which layer/module it belongs to (by directory match against
layer_orderorplacement_rules). - Read its imports / use statements.
- Verify each import targets the same or a lower layer (using
layer_order).
- Identify which layer/module it belongs to (by directory match against
- For each new file:
- Verify it lives in a directory permitted by
placement_rules. - Verify any role-specific shape (e.g. "tool functions take a context parameter") if such a rule is declared.
- Verify it lives in a directory permitted by
- For convention rules from the
Conventionssection:- Grep changed files for forbidden patterns (e.g. bare exception raises, direct
printif logging is required).
- Grep changed files for forbidden patterns (e.g. bare exception raises, direct
Generic fallback (no project rules declared)
If no Architectural Rules are defined, perform only universal checks:
- No new circular imports introduced (
<source_dirs>→<source_dirs>cycles). - No deeply nested
..parent traversals in import paths. - No duplicated public symbols added by accident (collision with existing exports in the same package).
Output
Report a table:
| File | Rule | Status | Detail |
|---|---|---|---|
<project-relative path> |
layer_order | PASS / FAIL |
If everything passes, report COMPLIANT with a one-line summary.
If anything fails, report VIOLATIONS FOUND with severity (CRITICAL / WARNING / INFO) and a specific fix suggestion per row.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 60 lines · 20 tokens per session scan A 0ea3497f9768
arch-reviewer is an agent published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 536 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.